finetuned-potato-leaf

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0551
• Accuracy: 0.9881

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 20
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.4036	1.0	187	0.3479	0.9511
0.2705	2.0	374	0.2260	0.9668
0.2044	3.0	561	0.1731	0.9706
0.1497	4.0	748	0.1374	0.9748
0.1493	5.0	935	0.1148	0.9801
0.1453	6.0	1122	0.0993	0.9824
0.1148	7.0	1309	0.0922	0.9820
0.1366	8.0	1496	0.0866	0.9848
0.1172	9.0	1683	0.0726	0.9867
0.1114	10.0	1870	0.0715	0.9843
0.0786	11.0	2057	0.0646	0.9881
0.0729	12.0	2244	0.0637	0.9867
0.0691	13.0	2431	0.0617	0.9867
0.0726	14.0	2618	0.0587	0.9867
0.0925	15.0	2805	0.0551	0.9881
0.0756	16.0	2992	0.0601	0.9858
0.0617	17.0	3179	0.0611	0.9848
0.065	18.0	3366	0.0576	0.9872

Framework versions

• Transformers 4.38.1
• Pytorch 2.1.2
• Datasets 2.1.0
• Tokenizers 0.15.2